Research Article
Moving Vehicle Detection and Classification Using Gaussian Mixture Model and Ensemble Deep Learning Technique
Table 3
Performance analysis of the proposed ensemble deep learning technique on the BIT Vehicle Dataset in terms of FDR and FOR.
| Feature extraction | Classifier | FDR (%) | FOR (%) |
| SPT | MSVM | 34.7 | 20.91 | KNN | 20 | 34.72 | DNN | 28 | 22 | LSTM | 18.90 | 17 | Ensemble | 11.02 | 12 | WLD | MSVM | 29 | 18.42 | KNN | 29.98 | 14 | DNN | 24 | 13.18 | LSTM | 18.07 | 7.2 | Ensemble | 12.03 | 6.5 | Hybrid (SPT + WLD) | MSVM | 13 | 11 | KNN | 9 | 5.01 | DNN | 7.67 | 3.10 | LSTM | 6.65 | 2.87 | Ensemble | 3.92 | 1.90 |
|
|